The research improves smart storage technology and material handling options

0

A group of faculty researchers built a prototype autonomous forklift truck with embedded systems to advance smart warehousing systems. Credit: Elizabeth Lamark/RIT

Industrial robots in warehouses will soon be smart enough to know who has the right of way in busy aisles.

Researchers at the Rochester Institute of Technology are developing a smart warehouse material handling system that integrates smart technologies like LiDAR sensors and artificial intelligence.

With supply chain challenges brought on by the pandemic and increased demand for e-commerce, technology can provide the support businesses need to improve productivity, efficiency and safety in a warehouse environment.

“This is an area where robotics and autonomous material handling can help,” said Michael Kuhl, professor of economics and systems engineering in Kate Gleason College of Engineering at RIT. “Robots can work longer periods of time – not necessarily to replace jobs, but for some of the manual, non-value-added tasks. It means a shift in the focus of work as humans are needed to design and maintain fleets of vehicles and robots.”

Kuhl and the project team received a grant for “Effective and Efficient Driving for Material Handling,” a year-long, $300,000 project funded by The Raymond Corp. is sponsored. It furthers previous work with the company that established task selection and path planning for single autonomous robots (AMR).

New work focuses on advanced avoidance and communication strategies for multiple robots and humans in the camp environment.

Warehouse operations often have a mix of autonomous and human-operated equipment. Avoidance strategies need to be integrated with task options, path planning, and detection of multiple robots that can communicate with each other in real-time, and to detect humans that will also be interacting in the storeroom.

“We have information about localization, the different types of sensors we use within the warehouse to try to identify the location of the robots, and the robot’s actual movement,” Kuhl said. “Can they plan to get from their current location to their destination safely and efficiently? They can have a short path but still have to avoid other robots and humans.”

Using deep neural network strategies (types of machine learning techniques), the system components are trained to make specific, sequenced decisions based on common tasks, but also rare or unusual actions that may occur in the warehouse environment.

The team is also examining the communication networks within the camp – WiFi and cellular network technology functions – as viable solutions. Kuhl explained that new standards for mobile radio technologies allow increased individual mobile radio communication between individual devices.

“In terms of human-vehicle interaction, could we use the sensors of multiple vehicles moving around the warehouse?” he said. “If a vehicle is coming down a path and sees a person or other vehicle coming out of an aisle, can they communicate and make a decision about what to do next? Who has the right of way?”

The team discovered that robots can react.

In field experiments Simcona Electronics Corp.a Rochester-based company that sources and sources electrical and mechanical components for manufacturing, the team is testing robotic technology at its 50,000-square-foot facility.

“We needed the real environment to be able to do this work and move it forward. They are an extremely valuable resource for us,” said Kuhl. He has worked with campus partners Amlan Ganguly, Associate Professor and Head of Department, and Andres Kwasinksi, Professor, both in the Department of Computer Engineering at RIT’s Kate Gleason College of Engineering; and Clark Hochgraf, Associate Professor in the Department of Electrical and Computer Engineering at RIT College of Engineering Technology. Also on the project team is Maojia Li, a recent RIT engineering PhD student.

Share the article on social media or via email:

Share.

Comments are closed.